Instructions to use Mininglamp-2718/Mano-CUA-4B-Thinking-1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mininglamp-2718/Mano-CUA-4B-Thinking-1.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Mininglamp-2718/Mano-CUA-4B-Thinking-1.1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Mininglamp-2718/Mano-CUA-4B-Thinking-1.1")
model = AutoModelForImageTextToText.from_pretrained("Mininglamp-2718/Mano-CUA-4B-Thinking-1.1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mininglamp-2718/Mano-CUA-4B-Thinking-1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mininglamp-2718/Mano-CUA-4B-Thinking-1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mininglamp-2718/Mano-CUA-4B-Thinking-1.1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Mininglamp-2718/Mano-CUA-4B-Thinking-1.1

SGLang

How to use Mininglamp-2718/Mano-CUA-4B-Thinking-1.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Mininglamp-2718/Mano-CUA-4B-Thinking-1.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mininglamp-2718/Mano-CUA-4B-Thinking-1.1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Mininglamp-2718/Mano-CUA-4B-Thinking-1.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mininglamp-2718/Mano-CUA-4B-Thinking-1.1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Mininglamp-2718/Mano-CUA-4B-Thinking-1.1 with Docker Model Runner:
```
docker model run hf.co/Mininglamp-2718/Mano-CUA-4B-Thinking-1.1
```

Mano-CUA-4B-Thinking-1.1 / .ms_upload_cache

hhhhhalf

Upload fp16 model ckpt124146 (Qwen3-VL 4B thinking)

addc233 verified 6 days ago

raw

history blame contribute delete

2.31 kB

{"version": 3, "repo_id": "Mininglamp2718/Mano-CUA-4B-Thinking-1.1", "files": {"./added_tokens.json|1779823843.447136|707": {"hash": "c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680", "size": 707, "status": "c"}, "./chat_template.jinja|1779823843.692184|5199": {"hash": "36e042fe45641f067b1f2381fcc8955d10d956a3ed333ecdf7f7eb0916f68956", "size": 5199, "status": "c"}, "./config.json|1779823831.904846|1652": {"hash": "e77bfbbd27c191e4b0812720b54b14612610358f9c48dc38f24fd2885aa937f5", "size": 1652, "status": "c"}, "./model.safetensors.index.json|1779823843.381401|64774": {"hash": "9c7edb1ea2595593e6e0adbefe8815dee0d82675578a4a478c2fc87c8428c482", "size": 64774, "status": "c"}, "./generation_config.json|1779823844.212358|192": {"hash": "38d193eee59c0d7815da874c73b0e4f65ab2c31c5eef50f14bfa2ef34929b0db", "size": 192, "status": "c"}, "./merges.txt|1779823843.53496|1671853": {"hash": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5", "size": 1671853, "status": "c"}, "./special_tokens_map.json|1779823843.440927|613": {"hash": "76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd", "size": 613, "status": "c"}, "./preprocessor_config.json|1779823844.189684|390": {"hash": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516", "size": 390, "status": "c"}, "./tokenizer_config.json|1779823843.435192|5445": {"hash": "81ec7bb9530159b326c0bef1d0b6c33d392090524014ea3f0123a3c1eb9c2af5", "size": 5445, "status": "c"}, "./tokenizer.json|1779823843.66584|11422654": {"hash": "aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4", "size": 11422654, "status": "c"}, "./video_preprocessor_config.json|1779823843.681738|817": {"hash": "59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1", "size": 817, "status": "c"}, "./vocab.json|1779823843.543373|2776833": {"hash": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910", "size": 2776833, "status": "c"}, "./model-00002-of-00002.safetensors|1779823843.023416|3885221448": {"hash": "cbadff579f56f18122fee8dfc14c25025d24283c56470247a30a7abc78af63fe", "size": 3885221448, "status": "c"}, "./model-00001-of-00002.safetensors|1779823837.860481|4990497880": {"hash": "0b7ee1d3fa37954e26d6921b040394cdce9678a505037126b2c94e291617fd87", "size": 4990497880, "status": "c"}}}